From 706cfffebd0cc41d1efb59128d55004e66889019 Mon Sep 17 00:00:00 2001 From: "opencode-agent[bot]" <219766164+opencode-agent[bot]@users.noreply.github.com> Date: Thu, 20 Aug 2026 18:27:40 +0000 Subject: [PATCH] chore(sync): update Requesty model catalog (#5143) Co-authored-by: opencode-agent[bot] --- providers/requesty/models/claude-fable-5.toml | 8 ++++---- providers/requesty/models/claude-fable-5@eu.toml | 8 ++++---- providers/requesty/models/claude-haiku-4-5.toml | 8 ++++---- .../requesty/models/claude-haiku-4-5@eu.toml | 8 ++++---- providers/requesty/models/claude-opus-4-1.toml | 8 ++++---- providers/requesty/models/claude-opus-4-5.toml | 8 ++++---- .../requesty/models/claude-opus-4-5@eu.toml | 8 ++++---- providers/requesty/models/claude-opus-4-6.toml | 8 ++++---- .../requesty/models/claude-opus-4-6@eu.toml | 8 ++++---- providers/requesty/models/claude-opus-4-7.toml | 8 ++++---- .../requesty/models/claude-opus-4-7@eu.toml | 8 ++++---- providers/requesty/models/claude-opus-4-8.toml | 8 ++++---- .../requesty/models/claude-opus-4-8@eu.toml | 8 ++++---- providers/requesty/models/claude-opus-5.toml | 8 ++++---- providers/requesty/models/claude-opus-5@eu.toml | 8 ++++---- providers/requesty/models/claude-sonnet-4-5.toml | 16 ++++++++-------- .../requesty/models/claude-sonnet-4-5@eu.toml | 16 ++++++++-------- providers/requesty/models/claude-sonnet-4-6.toml | 8 ++++---- .../requesty/models/claude-sonnet-4-6@eu.toml | 8 ++++---- .../requesty/models/claude-sonnet-4@eu.toml | 16 ++++++++-------- providers/requesty/models/claude-sonnet-5.toml | 8 ++++---- .../requesty/models/claude-sonnet-5@eu.toml | 8 ++++---- .../requesty/models/deepseek-v4-flash-0731.toml | 6 +++--- .../models/deepseek-v4-flash-0731@eu.toml | 6 +++--- providers/requesty/models/deepseek-v4-flash.toml | 6 +++--- .../requesty/models/deepseek-v4-pro-0813.toml | 6 +++--- providers/requesty/models/deepseek-v4-pro.toml | 6 +++--- .../requesty/models/deepseek-v4-pro@eu.toml | 6 +++--- providers/requesty/models/devstral-latest.toml | 6 +++--- .../requesty/models/devstral-latest@eu.toml | 6 +++--- providers/requesty/models/fugu-ultra.toml | 12 ++++++------ .../requesty/models/gemini-2.5-flash@eu.toml | 8 ++++---- .../requesty/models/gemini-3-pro-image.toml | 16 ++++++++-------- .../requesty/models/gemini-3.1-flash-image.toml | 8 ++++---- .../requesty/models/gemini-3.1-flash-lite.toml | 16 ++++++++-------- .../models/gemini-3.1-flash-lite@eu.toml | 16 ++++++++-------- .../requesty/models/gemini-3.1-pro-preview.toml | 16 ++++++++-------- .../requesty/models/gemini-3.5-flash-lite.toml | 6 +++--- .../models/gemini-3.5-flash-lite@eu.toml | 6 +++--- providers/requesty/models/gemini-3.5-flash.toml | 8 ++++---- .../requesty/models/gemini-3.5-flash@eu.toml | 8 ++++---- providers/requesty/models/gemini-3.6-flash.toml | 6 +++--- providers/requesty/models/gemini-3.7-flash.toml | 6 +++--- .../requesty/models/gemini-3.7-flash@eu.toml | 6 +++--- .../requesty/models/gemma-4-26b-a4b-it.toml | 6 +++--- providers/requesty/models/glm-5.1.toml | 6 +++--- providers/requesty/models/glm-5.1@eu.toml | 6 +++--- providers/requesty/models/glm-5.2-fast.toml | 6 +++--- providers/requesty/models/glm-5.2.toml | 6 +++--- providers/requesty/models/glm-5.2@eu.toml | 6 +++--- providers/requesty/models/glm-5.3.toml | 6 +++--- providers/requesty/models/gpt-4.1-mini@eu.toml | 6 +++--- providers/requesty/models/gpt-4.1-nano@eu.toml | 6 +++--- providers/requesty/models/gpt-4.1@eu.toml | 6 +++--- providers/requesty/models/gpt-4o-mini@eu.toml | 6 +++--- providers/requesty/models/gpt-5-mini@eu.toml | 6 +++--- providers/requesty/models/gpt-5-nano@eu.toml | 6 +++--- providers/requesty/models/gpt-5.1@eu.toml | 6 +++--- providers/requesty/models/gpt-5.3-chat.toml | 6 +++--- providers/requesty/models/gpt-5.3-codex.toml | 6 +++--- providers/requesty/models/gpt-5.4-mini.toml | 6 +++--- providers/requesty/models/gpt-5.4-nano.toml | 6 +++--- providers/requesty/models/gpt-5.4-pro.toml | 6 +++--- providers/requesty/models/gpt-5.4.toml | 6 +++--- providers/requesty/models/gpt-5.4@eu.toml | 12 ++++++------ providers/requesty/models/gpt-5.5-pro.toml | 4 ++-- providers/requesty/models/gpt-5.5.toml | 6 +++--- providers/requesty/models/gpt-5.5@eu.toml | 12 ++++++------ providers/requesty/models/gpt-5.6-luna.toml | 12 ++++++------ providers/requesty/models/gpt-5.6-luna@eu.toml | 6 +++--- providers/requesty/models/gpt-5.6-sol.toml | 12 ++++++------ providers/requesty/models/gpt-5.6-sol@eu.toml | 6 +++--- providers/requesty/models/gpt-5.6-terra.toml | 12 ++++++------ providers/requesty/models/gpt-5.6-terra@eu.toml | 6 +++--- providers/requesty/models/gpt-5@eu.toml | 6 +++--- providers/requesty/models/grok-4.2-beta.toml | 16 ++++++++-------- providers/requesty/models/grok-4.3.toml | 16 ++++++++-------- providers/requesty/models/grok-4.5.toml | 16 ++++++++-------- providers/requesty/models/grok-4.6.toml | 16 ++++++++-------- providers/requesty/models/grok-build-0.1.toml | 6 +++--- providers/requesty/models/hy3.toml | 6 +++--- providers/requesty/models/inkling-256k.toml | 6 +++--- providers/requesty/models/inkling.toml | 6 +++--- providers/requesty/models/kat-coder-pro.toml | 4 ++-- providers/requesty/models/kimi-k2.6.toml | 6 +++--- providers/requesty/models/kimi-k2.6@eu.toml | 6 +++--- providers/requesty/models/kimi-k2.7-code.toml | 6 +++--- providers/requesty/models/kimi-k2.7-code@eu.toml | 6 +++--- providers/requesty/models/kimi-k3.toml | 6 +++--- providers/requesty/models/kimi-k3@eu.toml | 6 +++--- providers/requesty/models/ling-2.6-1t.toml | 4 ++-- providers/requesty/models/ling-2.6-flash.toml | 4 ++-- providers/requesty/models/mimo-v2.5-pro.toml | 6 +++--- providers/requesty/models/mimo-v2.5.toml | 6 +++--- .../requesty/models/minimax-m2.7-highspeed.toml | 8 ++++---- providers/requesty/models/minimax-m2.7.toml | 8 ++++---- providers/requesty/models/minimax-m3.toml | 6 +++--- providers/requesty/models/minimax-m3@eu.toml | 6 +++--- .../requesty/models/mistral-medium-3-5.toml | 6 +++--- .../requesty/models/mistral-medium-3-5@eu.toml | 6 +++--- .../requesty/models/mistral-medium-latest.toml | 6 +++--- .../models/mistral-medium-latest@eu.toml | 6 +++--- .../requesty/models/mistral-small-2603.toml | 6 +++--- .../requesty/models/mistral-small-2603@eu.toml | 6 +++--- .../requesty/models/nemotron-3-nano-omni.toml | 6 +++--- .../requesty/models/nemotron-3-nano-omni@eu.toml | 6 +++--- .../requesty/models/nemotron-3-ultra-nvfp4.toml | 6 +++--- .../models/nemotron-lightning-3.5-30b-a3b.toml | 6 +++--- .../nvidia-nemotron-3-super-120b-a12b.toml | 4 ++-- .../requesty/models/nvidia-nemotron-3-ultra.toml | 4 ++-- providers/requesty/models/o4-mini@eu.toml | 6 +++--- providers/requesty/models/qwen3.5-27b.toml | 4 ++-- providers/requesty/models/qwen3.5-2b.toml | 4 ++-- providers/requesty/models/qwen3.5-35b-a3b.toml | 6 +++--- providers/requesty/models/qwen3.6-plus.toml | 8 ++++---- providers/requesty/models/qwen3.7-max.toml | 8 ++++---- providers/requesty/models/qwen3.7-plus.toml | 8 ++++---- providers/requesty/models/qwen3.8-2.4T-A95B.toml | 6 +++--- providers/requesty/models/qwen3.8-max.toml | 8 ++++---- providers/requesty/models/ring-2.6-1t.toml | 4 ++-- providers/requesty/models/seed-1.8.toml | 6 +++--- providers/requesty/models/seed-2.0-code.toml | 6 +++--- providers/requesty/models/seed-2.0-mini.toml | 6 +++--- providers/requesty/models/seed-2.0-pro.toml | 6 +++--- providers/requesty/models/step-3.7-flash.toml | 6 +++--- .../requesty/models/thinkingcap-qwen3.6-27b.toml | 6 +++--- .../models/thinkingcap-qwen3.6-27b@eu.toml | 6 +++--- 127 files changed, 474 insertions(+), 474 deletions(-) diff --git a/providers/requesty/models/claude-fable-5.toml b/providers/requesty/models/claude-fable-5.toml index 685f20fb0..e2a107d88 100644 --- a/providers/requesty/models/claude-fable-5.toml +++ b/providers/requesty/models/claude-fable-5.toml @@ -9,7 +9,7 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 10 -output = 50 -cache_read = 1 -cache_write = 12.5 +input = 9 +output = 45 +cache_read = 0.9 +cache_write = 11.25 diff --git a/providers/requesty/models/claude-fable-5@eu.toml b/providers/requesty/models/claude-fable-5@eu.toml index 7e5d5f41f..35f9764cd 100644 --- a/providers/requesty/models/claude-fable-5@eu.toml +++ b/providers/requesty/models/claude-fable-5@eu.toml @@ -10,7 +10,7 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 11 -output = 55 -cache_read = 1.1 -cache_write = 13.75 +input = 9.9 +output = 49.5 +cache_read = 0.99 +cache_write = 12.375 diff --git a/providers/requesty/models/claude-haiku-4-5.toml b/providers/requesty/models/claude-haiku-4-5.toml index ef99a1dbd..67ec34cf7 100644 --- a/providers/requesty/models/claude-haiku-4-5.toml +++ b/providers/requesty/models/claude-haiku-4-5.toml @@ -9,7 +9,7 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 1 -output = 5 -cache_read = 0.1 -cache_write = 1.25 +input = 0.9 +output = 4.5 +cache_read = 0.09 +cache_write = 1.125 diff --git a/providers/requesty/models/claude-haiku-4-5@eu.toml b/providers/requesty/models/claude-haiku-4-5@eu.toml index db3821994..5cc8db46c 100644 --- a/providers/requesty/models/claude-haiku-4-5@eu.toml +++ b/providers/requesty/models/claude-haiku-4-5@eu.toml @@ -10,7 +10,7 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 1.1 -output = 5.5 -cache_read = 0.11 -cache_write = 1.375 +input = 0.99 +output = 4.95 +cache_read = 0.099 +cache_write = 1.2375 diff --git a/providers/requesty/models/claude-opus-4-1.toml b/providers/requesty/models/claude-opus-4-1.toml index bde914f89..18401d206 100644 --- a/providers/requesty/models/claude-opus-4-1.toml +++ b/providers/requesty/models/claude-opus-4-1.toml @@ -9,7 +9,7 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 15 -output = 75 -cache_read = 1.5 -cache_write = 18.75 +input = 13.5 +output = 67.5 +cache_read = 1.35 +cache_write = 16.875 diff --git a/providers/requesty/models/claude-opus-4-5.toml b/providers/requesty/models/claude-opus-4-5.toml index f00d78dd6..222b87f29 100644 --- a/providers/requesty/models/claude-opus-4-5.toml +++ b/providers/requesty/models/claude-opus-4-5.toml @@ -9,7 +9,7 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 5 -output = 25 -cache_read = 0.5 -cache_write = 6.25 +input = 4.5 +output = 22.5 +cache_read = 0.45 +cache_write = 5.625 diff --git a/providers/requesty/models/claude-opus-4-5@eu.toml b/providers/requesty/models/claude-opus-4-5@eu.toml index 58430132a..93abb7188 100644 --- a/providers/requesty/models/claude-opus-4-5@eu.toml +++ b/providers/requesty/models/claude-opus-4-5@eu.toml @@ -10,7 +10,7 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 5.5 -output = 27.5 -cache_read = 0.55 -cache_write = 6.875 +input = 4.95 +output = 24.75 +cache_read = 0.495 +cache_write = 6.1875 diff --git a/providers/requesty/models/claude-opus-4-6.toml b/providers/requesty/models/claude-opus-4-6.toml index e43a8709a..b82af39fe 100644 --- a/providers/requesty/models/claude-opus-4-6.toml +++ b/providers/requesty/models/claude-opus-4-6.toml @@ -9,7 +9,7 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 5 -output = 25 -cache_read = 0.5 -cache_write = 6.25 +input = 4.5 +output = 22.5 +cache_read = 0.45 +cache_write = 5.625 diff --git a/providers/requesty/models/claude-opus-4-6@eu.toml b/providers/requesty/models/claude-opus-4-6@eu.toml index f5e449652..56d580490 100644 --- a/providers/requesty/models/claude-opus-4-6@eu.toml +++ b/providers/requesty/models/claude-opus-4-6@eu.toml @@ -10,7 +10,7 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 5.5 -output = 27.5 -cache_read = 0.55 -cache_write = 6.875 +input = 4.95 +output = 24.75 +cache_read = 0.495 +cache_write = 6.1875 diff --git a/providers/requesty/models/claude-opus-4-7.toml b/providers/requesty/models/claude-opus-4-7.toml index 4c464ebf7..9b33e0c52 100644 --- a/providers/requesty/models/claude-opus-4-7.toml +++ b/providers/requesty/models/claude-opus-4-7.toml @@ -9,7 +9,7 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 5 -output = 25 -cache_read = 0.5 -cache_write = 6.25 +input = 4.5 +output = 22.5 +cache_read = 0.45 +cache_write = 5.625 diff --git a/providers/requesty/models/claude-opus-4-7@eu.toml b/providers/requesty/models/claude-opus-4-7@eu.toml index b2067197c..514bce6a5 100644 --- a/providers/requesty/models/claude-opus-4-7@eu.toml +++ b/providers/requesty/models/claude-opus-4-7@eu.toml @@ -10,7 +10,7 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 5.5 -output = 27.5 -cache_read = 0.55 -cache_write = 6.875 +input = 4.95 +output = 24.75 +cache_read = 0.495 +cache_write = 6.1875 diff --git a/providers/requesty/models/claude-opus-4-8.toml b/providers/requesty/models/claude-opus-4-8.toml index 32911565b..a77ef72f1 100644 --- a/providers/requesty/models/claude-opus-4-8.toml +++ b/providers/requesty/models/claude-opus-4-8.toml @@ -9,7 +9,7 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 5 -output = 25 -cache_read = 0.5 -cache_write = 6.25 +input = 4.5 +output = 22.5 +cache_read = 0.45 +cache_write = 5.625 diff --git a/providers/requesty/models/claude-opus-4-8@eu.toml b/providers/requesty/models/claude-opus-4-8@eu.toml index af4708b3b..ec2bef267 100644 --- a/providers/requesty/models/claude-opus-4-8@eu.toml +++ b/providers/requesty/models/claude-opus-4-8@eu.toml @@ -10,7 +10,7 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 5.5 -output = 27.5 -cache_read = 0.55 -cache_write = 6.875 +input = 4.95 +output = 24.75 +cache_read = 0.495 +cache_write = 6.1875 diff --git a/providers/requesty/models/claude-opus-5.toml b/providers/requesty/models/claude-opus-5.toml index 5807ccae2..b765dada3 100644 --- a/providers/requesty/models/claude-opus-5.toml +++ b/providers/requesty/models/claude-opus-5.toml @@ -9,7 +9,7 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 5 -output = 25 -cache_read = 0.5 -cache_write = 6.25 +input = 4.5 +output = 22.5 +cache_read = 0.45 +cache_write = 5.625 diff --git a/providers/requesty/models/claude-opus-5@eu.toml b/providers/requesty/models/claude-opus-5@eu.toml index efe076651..f78e6d571 100644 --- a/providers/requesty/models/claude-opus-5@eu.toml +++ b/providers/requesty/models/claude-opus-5@eu.toml @@ -10,7 +10,7 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 5.5 -output = 27.5 -cache_read = 0.55 -cache_write = 6.875 +input = 4.95 +output = 24.75 +cache_read = 0.495 +cache_write = 6.1875 diff --git a/providers/requesty/models/claude-sonnet-4-5.toml b/providers/requesty/models/claude-sonnet-4-5.toml index fb2d6fa1c..c509d9f17 100644 --- a/providers/requesty/models/claude-sonnet-4-5.toml +++ b/providers/requesty/models/claude-sonnet-4-5.toml @@ -9,17 +9,17 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 3 -output = 15 -cache_read = 0.3 -cache_write = 3.75 +input = 2.7 +output = 13.5 +cache_read = 0.27 +cache_write = 3.375 [[cost.tiers]] tier = { type = "context", size = 200_000 } -input = 6 -output = 22.5 -cache_read = 0.6 -cache_write = 7.5 +input = 5.4 +output = 20.25 +cache_read = 0.54 +cache_write = 6.75 [limit] context = 1_000_000 diff --git a/providers/requesty/models/claude-sonnet-4-5@eu.toml b/providers/requesty/models/claude-sonnet-4-5@eu.toml index cadc9b45b..418061c55 100644 --- a/providers/requesty/models/claude-sonnet-4-5@eu.toml +++ b/providers/requesty/models/claude-sonnet-4-5@eu.toml @@ -10,17 +10,17 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 3.3 -output = 16.5 -cache_read = 0.3 -cache_write = 4.125 +input = 2.97 +output = 14.85 +cache_read = 0.27 +cache_write = 3.7125 [[cost.tiers]] tier = { type = "context", size = 200_000 } -input = 6.6 -output = 24.75 -cache_read = 0.6 -cache_write = 8.25 +input = 5.94 +output = 22.275 +cache_read = 0.54 +cache_write = 7.425 [limit] context = 1_000_000 diff --git a/providers/requesty/models/claude-sonnet-4-6.toml b/providers/requesty/models/claude-sonnet-4-6.toml index 011600033..33f7728a6 100644 --- a/providers/requesty/models/claude-sonnet-4-6.toml +++ b/providers/requesty/models/claude-sonnet-4-6.toml @@ -9,10 +9,10 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 3 -output = 15 -cache_read = 0.3 -cache_write = 3.75 +input = 2.7 +output = 13.5 +cache_read = 0.27 +cache_write = 3.375 [limit] output = 128_000 diff --git a/providers/requesty/models/claude-sonnet-4-6@eu.toml b/providers/requesty/models/claude-sonnet-4-6@eu.toml index fb5415390..94e97bb86 100644 --- a/providers/requesty/models/claude-sonnet-4-6@eu.toml +++ b/providers/requesty/models/claude-sonnet-4-6@eu.toml @@ -10,7 +10,7 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 3.3 -output = 16.5 -cache_read = 0.3 -cache_write = 4.125 +input = 2.97 +output = 14.85 +cache_read = 0.27 +cache_write = 3.7125 diff --git a/providers/requesty/models/claude-sonnet-4@eu.toml b/providers/requesty/models/claude-sonnet-4@eu.toml index c66eab29d..082d254b6 100644 --- a/providers/requesty/models/claude-sonnet-4@eu.toml +++ b/providers/requesty/models/claude-sonnet-4@eu.toml @@ -10,17 +10,17 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 3 -output = 15 -cache_read = 0.3 -cache_write = 3.75 +input = 2.7 +output = 13.5 +cache_read = 0.27 +cache_write = 3.375 [[cost.tiers]] tier = { type = "context", size = 200_000 } -input = 6 -output = 22.5 -cache_read = 0.6 -cache_write = 7.5 +input = 5.4 +output = 20.25 +cache_read = 0.54 +cache_write = 6.75 [limit] context = 1_000_000 diff --git a/providers/requesty/models/claude-sonnet-5.toml b/providers/requesty/models/claude-sonnet-5.toml index ef0819722..b5edcbfe1 100644 --- a/providers/requesty/models/claude-sonnet-5.toml +++ b/providers/requesty/models/claude-sonnet-5.toml @@ -9,7 +9,7 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 2 -output = 10 -cache_read = 0.2 -cache_write = 2.5 +input = 1.8 +output = 9 +cache_read = 0.18 +cache_write = 2.25 diff --git a/providers/requesty/models/claude-sonnet-5@eu.toml b/providers/requesty/models/claude-sonnet-5@eu.toml index d4db42a62..e7592a831 100644 --- a/providers/requesty/models/claude-sonnet-5@eu.toml +++ b/providers/requesty/models/claude-sonnet-5@eu.toml @@ -10,7 +10,7 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 2.2 -output = 11 -cache_read = 0.22 -cache_write = 2.75 +input = 1.98 +output = 9.9 +cache_read = 0.198 +cache_write = 2.475 diff --git a/providers/requesty/models/deepseek-v4-flash-0731.toml b/providers/requesty/models/deepseek-v4-flash-0731.toml index d73d297b4..8509a5326 100644 --- a/providers/requesty/models/deepseek-v4-flash-0731.toml +++ b/providers/requesty/models/deepseek-v4-flash-0731.toml @@ -8,9 +8,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.14 -output = 0.28 -cache_read = 0.07 +input = 0.126 +output = 0.252 +cache_read = 0.063 [limit] context = 1_048_576 diff --git a/providers/requesty/models/deepseek-v4-flash-0731@eu.toml b/providers/requesty/models/deepseek-v4-flash-0731@eu.toml index e33044e46..50bdcdee8 100644 --- a/providers/requesty/models/deepseek-v4-flash-0731@eu.toml +++ b/providers/requesty/models/deepseek-v4-flash-0731@eu.toml @@ -9,9 +9,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.14 -output = 0.28 -cache_read = 0.07 +input = 0.126 +output = 0.252 +cache_read = 0.063 [limit] context = 1_048_576 diff --git a/providers/requesty/models/deepseek-v4-flash.toml b/providers/requesty/models/deepseek-v4-flash.toml index 991114cd0..cba6b291f 100644 --- a/providers/requesty/models/deepseek-v4-flash.toml +++ b/providers/requesty/models/deepseek-v4-flash.toml @@ -3,6 +3,6 @@ reasoning = false structured_output = false [cost] -input = 0.44 -output = 1.32 -cache_read = 0.014 +input = 0.396 +output = 1.188 +cache_read = 0.0126 diff --git a/providers/requesty/models/deepseek-v4-pro-0813.toml b/providers/requesty/models/deepseek-v4-pro-0813.toml index 117c7233a..80f2c6e61 100644 --- a/providers/requesty/models/deepseek-v4-pro-0813.toml +++ b/providers/requesty/models/deepseek-v4-pro-0813.toml @@ -8,9 +8,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 1.32 -output = 3.96 -cache_read = 0.044 +input = 1.188 +output = 3.564 +cache_read = 0.0396 [limit] output = 131_072 diff --git a/providers/requesty/models/deepseek-v4-pro.toml b/providers/requesty/models/deepseek-v4-pro.toml index 6b68c88eb..82bea369c 100644 --- a/providers/requesty/models/deepseek-v4-pro.toml +++ b/providers/requesty/models/deepseek-v4-pro.toml @@ -8,6 +8,6 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 1.32 -output = 3.96 -cache_read = 0.044 +input = 1.188 +output = 3.564 +cache_read = 0.0396 diff --git a/providers/requesty/models/deepseek-v4-pro@eu.toml b/providers/requesty/models/deepseek-v4-pro@eu.toml index 5ac0f1fe8..8d322b19c 100644 --- a/providers/requesty/models/deepseek-v4-pro@eu.toml +++ b/providers/requesty/models/deepseek-v4-pro@eu.toml @@ -9,9 +9,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 1.75 -output = 3.5 -cache_read = 0.44 +input = 1.575 +output = 3.15 +cache_read = 0.396 [limit] context = 1_048_576 diff --git a/providers/requesty/models/devstral-latest.toml b/providers/requesty/models/devstral-latest.toml index 6b8094c8f..3dd0b187e 100644 --- a/providers/requesty/models/devstral-latest.toml +++ b/providers/requesty/models/devstral-latest.toml @@ -10,9 +10,9 @@ structured_output = true open_weights = false [cost] -input = 0.44 -output = 2.2 -cache_read = 0.44 +input = 0.396 +output = 1.98 +cache_read = 0.396 [limit] context = 256_000 diff --git a/providers/requesty/models/devstral-latest@eu.toml b/providers/requesty/models/devstral-latest@eu.toml index 046e77dee..040860df3 100644 --- a/providers/requesty/models/devstral-latest@eu.toml +++ b/providers/requesty/models/devstral-latest@eu.toml @@ -10,9 +10,9 @@ structured_output = true open_weights = false [cost] -input = 0.44 -output = 2.2 -cache_read = 0.44 +input = 0.396 +output = 1.98 +cache_read = 0.396 [limit] context = 256_000 diff --git a/providers/requesty/models/fugu-ultra.toml b/providers/requesty/models/fugu-ultra.toml index bc82853c1..a36b7df3b 100644 --- a/providers/requesty/models/fugu-ultra.toml +++ b/providers/requesty/models/fugu-ultra.toml @@ -3,15 +3,15 @@ reasoning = false structured_output = false [cost] -input = 5 -output = 30 -cache_read = 0.5 +input = 4.5 +output = 27 +cache_read = 0.45 [[cost.tiers]] tier = { type = "context", size = 272_000 } -input = 10 -output = 45 -cache_read = 1 +input = 9 +output = 40.5 +cache_read = 0.9 [limit] context = 1_048_576 diff --git a/providers/requesty/models/gemini-2.5-flash@eu.toml b/providers/requesty/models/gemini-2.5-flash@eu.toml index fdf531313..2416c4284 100644 --- a/providers/requesty/models/gemini-2.5-flash@eu.toml +++ b/providers/requesty/models/gemini-2.5-flash@eu.toml @@ -9,10 +9,10 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.3 -output = 2.5 -cache_read = 0.075 -cache_write = 0.55 +input = 0.27 +output = 2.25 +cache_read = 0.0675 +cache_write = 0.495 [limit] output = 65_535 diff --git a/providers/requesty/models/gemini-3-pro-image.toml b/providers/requesty/models/gemini-3-pro-image.toml index 21eb5f8c6..7adf6cd3c 100644 --- a/providers/requesty/models/gemini-3-pro-image.toml +++ b/providers/requesty/models/gemini-3-pro-image.toml @@ -10,17 +10,17 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 2 -output = 12 -cache_read = 0.2 -cache_write = 4.5 +input = 1.8 +output = 10.8 +cache_read = 0.18 +cache_write = 4.05 [[cost.tiers]] tier = { type = "context", size = 200_000 } -input = 4 -output = 18 -cache_read = 0.2 -cache_write = 4.5 +input = 3.6 +output = 16.2 +cache_read = 0.18 +cache_write = 4.05 [limit] context = 1_048_576 diff --git a/providers/requesty/models/gemini-3.1-flash-image.toml b/providers/requesty/models/gemini-3.1-flash-image.toml index c3b869b37..9d3631718 100644 --- a/providers/requesty/models/gemini-3.1-flash-image.toml +++ b/providers/requesty/models/gemini-3.1-flash-image.toml @@ -10,10 +10,10 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.5 -output = 2 +input = 0.45 +output = 1.8 [[cost.tiers]] tier = { type = "context", size = 200_000 } -input = 0.5 -output = 2 +input = 0.45 +output = 1.8 diff --git a/providers/requesty/models/gemini-3.1-flash-lite.toml b/providers/requesty/models/gemini-3.1-flash-lite.toml index f45173eea..ffbedc9c3 100644 --- a/providers/requesty/models/gemini-3.1-flash-lite.toml +++ b/providers/requesty/models/gemini-3.1-flash-lite.toml @@ -8,17 +8,17 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.25 -output = 1.5 -cache_read = 0.025 -cache_write = 0.08333 +input = 0.225 +output = 1.35 +cache_read = 0.0225 +cache_write = 0.074997 [[cost.tiers]] tier = { type = "context", size = 200_000 } -input = 0.5 -output = 2.25 -cache_read = 0.025 -cache_write = 0.08333 +input = 0.45 +output = 2.025 +cache_read = 0.0225 +cache_write = 0.074997 [limit] output = 65_535 diff --git a/providers/requesty/models/gemini-3.1-flash-lite@eu.toml b/providers/requesty/models/gemini-3.1-flash-lite@eu.toml index a51707905..7e6b034a5 100644 --- a/providers/requesty/models/gemini-3.1-flash-lite@eu.toml +++ b/providers/requesty/models/gemini-3.1-flash-lite@eu.toml @@ -9,17 +9,17 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.275 -output = 1.65 -cache_read = 0.0275 -cache_write = 0.091663 +input = 0.2475 +output = 1.485 +cache_read = 0.02475 +cache_write = 0.082497 [[cost.tiers]] tier = { type = "context", size = 200_000 } -input = 0.55 -output = 2.475 -cache_read = 0.0275 -cache_write = 0.091663 +input = 0.495 +output = 2.2275 +cache_read = 0.02475 +cache_write = 0.082497 [limit] output = 65_535 diff --git a/providers/requesty/models/gemini-3.1-pro-preview.toml b/providers/requesty/models/gemini-3.1-pro-preview.toml index 45392c263..56dc44aa6 100644 --- a/providers/requesty/models/gemini-3.1-pro-preview.toml +++ b/providers/requesty/models/gemini-3.1-pro-preview.toml @@ -8,17 +8,17 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 2 -output = 12 -cache_read = 0.2 -cache_write = 4.5 +input = 1.8 +output = 10.8 +cache_read = 0.18 +cache_write = 4.05 [[cost.tiers]] tier = { type = "context", size = 200_000 } -input = 4 -output = 18 -cache_read = 0.2 -cache_write = 4.5 +input = 3.6 +output = 16.2 +cache_read = 0.18 +cache_write = 4.05 [limit] output = 65_535 diff --git a/providers/requesty/models/gemini-3.5-flash-lite.toml b/providers/requesty/models/gemini-3.5-flash-lite.toml index 3373ffd06..c6aada13d 100644 --- a/providers/requesty/models/gemini-3.5-flash-lite.toml +++ b/providers/requesty/models/gemini-3.5-flash-lite.toml @@ -8,9 +8,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.3 -output = 2.5 -cache_read = 0.03 +input = 0.27 +output = 2.25 +cache_read = 0.027 [limit] output = 65_535 diff --git a/providers/requesty/models/gemini-3.5-flash-lite@eu.toml b/providers/requesty/models/gemini-3.5-flash-lite@eu.toml index e8db9e824..41fcc13f5 100644 --- a/providers/requesty/models/gemini-3.5-flash-lite@eu.toml +++ b/providers/requesty/models/gemini-3.5-flash-lite@eu.toml @@ -9,9 +9,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.33 -output = 2.75 -cache_read = 0.033 +input = 0.297 +output = 2.475 +cache_read = 0.0297 [limit] output = 65_535 diff --git a/providers/requesty/models/gemini-3.5-flash.toml b/providers/requesty/models/gemini-3.5-flash.toml index 905b0d8f7..2ecd96936 100644 --- a/providers/requesty/models/gemini-3.5-flash.toml +++ b/providers/requesty/models/gemini-3.5-flash.toml @@ -8,10 +8,10 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 1.5 -output = 9 -cache_read = 0.15 -cache_write = 1.583 +input = 1.35 +output = 8.1 +cache_read = 0.135 +cache_write = 1.4247 [limit] output = 65_535 diff --git a/providers/requesty/models/gemini-3.5-flash@eu.toml b/providers/requesty/models/gemini-3.5-flash@eu.toml index 60cb1f724..28011a05c 100644 --- a/providers/requesty/models/gemini-3.5-flash@eu.toml +++ b/providers/requesty/models/gemini-3.5-flash@eu.toml @@ -9,10 +9,10 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 1.65 -output = 9.9 -cache_read = 0.165 -cache_write = 1.7413 +input = 1.485 +output = 8.91 +cache_read = 0.1485 +cache_write = 1.56717 [limit] output = 65_535 diff --git a/providers/requesty/models/gemini-3.6-flash.toml b/providers/requesty/models/gemini-3.6-flash.toml index 7d7082c48..656f28894 100644 --- a/providers/requesty/models/gemini-3.6-flash.toml +++ b/providers/requesty/models/gemini-3.6-flash.toml @@ -8,9 +8,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 1.5 -output = 7 -cache_read = 0.15 +input = 1.35 +output = 6.3 +cache_read = 0.135 [limit] output = 65_535 diff --git a/providers/requesty/models/gemini-3.7-flash.toml b/providers/requesty/models/gemini-3.7-flash.toml index 7a3857db1..2f1ca9bfd 100644 --- a/providers/requesty/models/gemini-3.7-flash.toml +++ b/providers/requesty/models/gemini-3.7-flash.toml @@ -8,9 +8,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.75 -output = 3.75 -cache_read = 0.075 +input = 0.6 +output = 3 +cache_read = 0.06 [limit] output = 65_535 diff --git a/providers/requesty/models/gemini-3.7-flash@eu.toml b/providers/requesty/models/gemini-3.7-flash@eu.toml index c7f3a15db..097d1384a 100644 --- a/providers/requesty/models/gemini-3.7-flash@eu.toml +++ b/providers/requesty/models/gemini-3.7-flash@eu.toml @@ -9,9 +9,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.825 -output = 4.125 -cache_read = 0.0825 +input = 0.66 +output = 3.3 +cache_read = 0.066 [limit] output = 65_535 diff --git a/providers/requesty/models/gemma-4-26b-a4b-it.toml b/providers/requesty/models/gemma-4-26b-a4b-it.toml index 923ea60bf..6c8e26054 100644 --- a/providers/requesty/models/gemma-4-26b-a4b-it.toml +++ b/providers/requesty/models/gemma-4-26b-a4b-it.toml @@ -8,9 +8,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.07 -output = 0.34 -cache_read = 0.07 +input = 0.063 +output = 0.306 +cache_read = 0.063 [limit] output = 262_144 diff --git a/providers/requesty/models/glm-5.1.toml b/providers/requesty/models/glm-5.1.toml index 1dd7588e5..76d3d1d30 100644 --- a/providers/requesty/models/glm-5.1.toml +++ b/providers/requesty/models/glm-5.1.toml @@ -9,9 +9,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 1.4 -output = 4.4 -cache_read = 0.26 +input = 1.26 +output = 3.96 +cache_read = 0.234 [limit] output = 128_000 diff --git a/providers/requesty/models/glm-5.1@eu.toml b/providers/requesty/models/glm-5.1@eu.toml index d4fb0081f..9e261e54b 100644 --- a/providers/requesty/models/glm-5.1@eu.toml +++ b/providers/requesty/models/glm-5.1@eu.toml @@ -9,9 +9,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 1.4 -output = 4.4 -cache_read = 1.4 +input = 1.26 +output = 3.96 +cache_read = 1.26 [limit] output = 200_000 diff --git a/providers/requesty/models/glm-5.2-fast.toml b/providers/requesty/models/glm-5.2-fast.toml index 48637ee68..85fd830a9 100644 --- a/providers/requesty/models/glm-5.2-fast.toml +++ b/providers/requesty/models/glm-5.2-fast.toml @@ -17,9 +17,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 2.1 -output = 6.6 -cache_read = 0.21 +input = 1.89 +output = 5.94 +cache_read = 0.189 [limit] context = 1_000_000 diff --git a/providers/requesty/models/glm-5.2.toml b/providers/requesty/models/glm-5.2.toml index bab0f699f..fa677c6eb 100644 --- a/providers/requesty/models/glm-5.2.toml +++ b/providers/requesty/models/glm-5.2.toml @@ -8,9 +8,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 1.2 -output = 4.2 -cache_read = 0.26 +input = 1.08 +output = 3.78 +cache_read = 0.234 [limit] context = 1_048_576 diff --git a/providers/requesty/models/glm-5.2@eu.toml b/providers/requesty/models/glm-5.2@eu.toml index 7d648ff7b..fe9f804d8 100644 --- a/providers/requesty/models/glm-5.2@eu.toml +++ b/providers/requesty/models/glm-5.2@eu.toml @@ -9,9 +9,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 1.2 -output = 4.2 -cache_read = 0.26 +input = 1.08 +output = 3.78 +cache_read = 0.234 [limit] context = 1_048_576 diff --git a/providers/requesty/models/glm-5.3.toml b/providers/requesty/models/glm-5.3.toml index baa2d5f55..e6d529faf 100644 --- a/providers/requesty/models/glm-5.3.toml +++ b/providers/requesty/models/glm-5.3.toml @@ -8,9 +8,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 1.4 -output = 4.4 -cache_read = 0.26 +input = 1.26 +output = 3.96 +cache_read = 0.234 [limit] output = 128_000 diff --git a/providers/requesty/models/gpt-4.1-mini@eu.toml b/providers/requesty/models/gpt-4.1-mini@eu.toml index 8f8e3096b..f0cc4b9b3 100644 --- a/providers/requesty/models/gpt-4.1-mini@eu.toml +++ b/providers/requesty/models/gpt-4.1-mini@eu.toml @@ -2,6 +2,6 @@ base_model = "openai/gpt-4.1-mini" name = "GPT-4.1 mini (EU)" [cost] -input = 0.44 -output = 1.76 -cache_read = 0.11 +input = 0.396 +output = 1.584 +cache_read = 0.099 diff --git a/providers/requesty/models/gpt-4.1-nano@eu.toml b/providers/requesty/models/gpt-4.1-nano@eu.toml index 69357d3eb..26ab9bbe2 100644 --- a/providers/requesty/models/gpt-4.1-nano@eu.toml +++ b/providers/requesty/models/gpt-4.1-nano@eu.toml @@ -2,6 +2,6 @@ base_model = "openai/gpt-4.1-nano" name = "GPT-4.1 nano (EU)" [cost] -input = 0.11 -output = 0.44 -cache_read = 0.0275 +input = 0.099 +output = 0.396 +cache_read = 0.02475 diff --git a/providers/requesty/models/gpt-4.1@eu.toml b/providers/requesty/models/gpt-4.1@eu.toml index 2bff8e5fc..7929c847f 100644 --- a/providers/requesty/models/gpt-4.1@eu.toml +++ b/providers/requesty/models/gpt-4.1@eu.toml @@ -2,6 +2,6 @@ base_model = "openai/gpt-4.1" name = "GPT-4.1 (EU)" [cost] -input = 2.2 -output = 8.8 -cache_read = 0.55 +input = 1.98 +output = 7.92 +cache_read = 0.495 diff --git a/providers/requesty/models/gpt-4o-mini@eu.toml b/providers/requesty/models/gpt-4o-mini@eu.toml index 9af1072d8..c20471482 100644 --- a/providers/requesty/models/gpt-4o-mini@eu.toml +++ b/providers/requesty/models/gpt-4o-mini@eu.toml @@ -2,9 +2,9 @@ base_model = "openai/gpt-4o-mini" name = "GPT-4o mini (EU)" [cost] -input = 0.165 -output = 0.66 -cache_read = 0.0825 +input = 0.1485 +output = 0.594 +cache_read = 0.07425 [limit] output = 16_000 diff --git a/providers/requesty/models/gpt-5-mini@eu.toml b/providers/requesty/models/gpt-5-mini@eu.toml index 5ebb06e4d..949de050d 100644 --- a/providers/requesty/models/gpt-5-mini@eu.toml +++ b/providers/requesty/models/gpt-5-mini@eu.toml @@ -10,9 +10,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.275 -output = 2.2 -cache_read = 0.0275 +input = 0.2475 +output = 1.98 +cache_read = 0.02475 [limit] context = 200_000 diff --git a/providers/requesty/models/gpt-5-nano@eu.toml b/providers/requesty/models/gpt-5-nano@eu.toml index 15ad36d15..6af0f44d3 100644 --- a/providers/requesty/models/gpt-5-nano@eu.toml +++ b/providers/requesty/models/gpt-5-nano@eu.toml @@ -10,9 +10,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.055 -output = 0.44 -cache_read = 0.0055 +input = 0.0495 +output = 0.396 +cache_read = 0.00495 [limit] context = 200_000 diff --git a/providers/requesty/models/gpt-5.1@eu.toml b/providers/requesty/models/gpt-5.1@eu.toml index e190b9c13..7cd1ddb24 100644 --- a/providers/requesty/models/gpt-5.1@eu.toml +++ b/providers/requesty/models/gpt-5.1@eu.toml @@ -9,6 +9,6 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 1.375 -output = 11 -cache_read = 0.1375 +input = 1.2375 +output = 9.9 +cache_read = 0.12375 diff --git a/providers/requesty/models/gpt-5.3-chat.toml b/providers/requesty/models/gpt-5.3-chat.toml index c2069c739..c045c9e2f 100644 --- a/providers/requesty/models/gpt-5.3-chat.toml +++ b/providers/requesty/models/gpt-5.3-chat.toml @@ -17,9 +17,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 1.75 -output = 14 -cache_read = 0.175 +input = 1.575 +output = 12.6 +cache_read = 0.1575 [limit] context = 128_000 diff --git a/providers/requesty/models/gpt-5.3-codex.toml b/providers/requesty/models/gpt-5.3-codex.toml index af89482ab..69bbfb229 100644 --- a/providers/requesty/models/gpt-5.3-codex.toml +++ b/providers/requesty/models/gpt-5.3-codex.toml @@ -8,6 +8,6 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 1.75 -output = 14 -cache_read = 0.175 +input = 1.575 +output = 12.6 +cache_read = 0.1575 diff --git a/providers/requesty/models/gpt-5.4-mini.toml b/providers/requesty/models/gpt-5.4-mini.toml index 44fdb6905..47ba8acea 100644 --- a/providers/requesty/models/gpt-5.4-mini.toml +++ b/providers/requesty/models/gpt-5.4-mini.toml @@ -8,6 +8,6 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.75 -output = 4.5 -cache_read = 0.075 +input = 0.675 +output = 4.05 +cache_read = 0.0675 diff --git a/providers/requesty/models/gpt-5.4-nano.toml b/providers/requesty/models/gpt-5.4-nano.toml index 3f0bd3d10..de9f1e15c 100644 --- a/providers/requesty/models/gpt-5.4-nano.toml +++ b/providers/requesty/models/gpt-5.4-nano.toml @@ -8,6 +8,6 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.2 -output = 1.25 -cache_read = 0.02 +input = 0.18 +output = 1.125 +cache_read = 0.018 diff --git a/providers/requesty/models/gpt-5.4-pro.toml b/providers/requesty/models/gpt-5.4-pro.toml index 9e8c264fe..a0772bd26 100644 --- a/providers/requesty/models/gpt-5.4-pro.toml +++ b/providers/requesty/models/gpt-5.4-pro.toml @@ -9,6 +9,6 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 30 -output = 180 -cache_read = 30 +input = 27 +output = 162 +cache_read = 27 diff --git a/providers/requesty/models/gpt-5.4.toml b/providers/requesty/models/gpt-5.4.toml index f11cbe1c5..acf18e0ae 100644 --- a/providers/requesty/models/gpt-5.4.toml +++ b/providers/requesty/models/gpt-5.4.toml @@ -8,6 +8,6 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 2.75 -output = 16.5 -cache_read = 0.275 +input = 2.475 +output = 14.85 +cache_read = 0.2475 diff --git a/providers/requesty/models/gpt-5.4@eu.toml b/providers/requesty/models/gpt-5.4@eu.toml index 60c008d3a..086b0c91c 100644 --- a/providers/requesty/models/gpt-5.4@eu.toml +++ b/providers/requesty/models/gpt-5.4@eu.toml @@ -9,12 +9,12 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 2.5 -output = 15 -cache_read = 0.25 +input = 2.25 +output = 13.5 +cache_read = 0.225 [[cost.tiers]] tier = { type = "context", size = 272_000 } -input = 5 -output = 22.5 -cache_read = 0.5 +input = 4.5 +output = 20.25 +cache_read = 0.45 diff --git a/providers/requesty/models/gpt-5.5-pro.toml b/providers/requesty/models/gpt-5.5-pro.toml index b1e1efca4..0e803920c 100644 --- a/providers/requesty/models/gpt-5.5-pro.toml +++ b/providers/requesty/models/gpt-5.5-pro.toml @@ -8,5 +8,5 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 30 -output = 180 +input = 27 +output = 162 diff --git a/providers/requesty/models/gpt-5.5.toml b/providers/requesty/models/gpt-5.5.toml index 28f1a5586..256baf26d 100644 --- a/providers/requesty/models/gpt-5.5.toml +++ b/providers/requesty/models/gpt-5.5.toml @@ -8,6 +8,6 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 5.5 -output = 33 -cache_read = 0.55 +input = 4.95 +output = 29.7 +cache_read = 0.495 diff --git a/providers/requesty/models/gpt-5.5@eu.toml b/providers/requesty/models/gpt-5.5@eu.toml index b0a78ccfa..2f37849b1 100644 --- a/providers/requesty/models/gpt-5.5@eu.toml +++ b/providers/requesty/models/gpt-5.5@eu.toml @@ -9,12 +9,12 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 5 -output = 30 -cache_read = 0.5 +input = 4.5 +output = 27 +cache_read = 0.45 [[cost.tiers]] tier = { type = "context", size = 272_000 } -input = 10 -output = 45 -cache_read = 1 +input = 9 +output = 40.5 +cache_read = 0.9 diff --git a/providers/requesty/models/gpt-5.6-luna.toml b/providers/requesty/models/gpt-5.6-luna.toml index 1d2484315..9623d14e7 100644 --- a/providers/requesty/models/gpt-5.6-luna.toml +++ b/providers/requesty/models/gpt-5.6-luna.toml @@ -8,12 +8,12 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.2 -output = 1.2 -cache_read = 0.02 +input = 0.18 +output = 1.08 +cache_read = 0.018 [[cost.tiers]] tier = { type = "context", size = 272_000 } -input = 0.4 -output = 1.8 -cache_read = 0.04 +input = 0.36 +output = 1.62 +cache_read = 0.036 diff --git a/providers/requesty/models/gpt-5.6-luna@eu.toml b/providers/requesty/models/gpt-5.6-luna@eu.toml index 9bf48d810..165b2e273 100644 --- a/providers/requesty/models/gpt-5.6-luna@eu.toml +++ b/providers/requesty/models/gpt-5.6-luna@eu.toml @@ -9,6 +9,6 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.22 -output = 1.32 -cache_read = 0.022 +input = 0.198 +output = 1.188 +cache_read = 0.0198 diff --git a/providers/requesty/models/gpt-5.6-sol.toml b/providers/requesty/models/gpt-5.6-sol.toml index e8740c1da..be8d51003 100644 --- a/providers/requesty/models/gpt-5.6-sol.toml +++ b/providers/requesty/models/gpt-5.6-sol.toml @@ -8,12 +8,12 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 5 -output = 30 -cache_read = 0.5 +input = 4.5 +output = 27 +cache_read = 0.45 [[cost.tiers]] tier = { type = "context", size = 272_000 } -input = 10 -output = 45 -cache_read = 1 +input = 9 +output = 40.5 +cache_read = 0.9 diff --git a/providers/requesty/models/gpt-5.6-sol@eu.toml b/providers/requesty/models/gpt-5.6-sol@eu.toml index ae290093a..5a42d7250 100644 --- a/providers/requesty/models/gpt-5.6-sol@eu.toml +++ b/providers/requesty/models/gpt-5.6-sol@eu.toml @@ -9,6 +9,6 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 5.5 -output = 33 -cache_read = 0.55 +input = 4.95 +output = 29.7 +cache_read = 0.495 diff --git a/providers/requesty/models/gpt-5.6-terra.toml b/providers/requesty/models/gpt-5.6-terra.toml index 72544acd7..c58e6be96 100644 --- a/providers/requesty/models/gpt-5.6-terra.toml +++ b/providers/requesty/models/gpt-5.6-terra.toml @@ -8,12 +8,12 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 2 -output = 12 -cache_read = 0.2 +input = 1.8 +output = 10.8 +cache_read = 0.18 [[cost.tiers]] tier = { type = "context", size = 272_000 } -input = 4 -output = 18 -cache_read = 0.4 +input = 3.6 +output = 16.2 +cache_read = 0.36 diff --git a/providers/requesty/models/gpt-5.6-terra@eu.toml b/providers/requesty/models/gpt-5.6-terra@eu.toml index d75520d24..88b926e3c 100644 --- a/providers/requesty/models/gpt-5.6-terra@eu.toml +++ b/providers/requesty/models/gpt-5.6-terra@eu.toml @@ -9,6 +9,6 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 2.2 -output = 13.2 -cache_read = 0.22 +input = 1.98 +output = 11.88 +cache_read = 0.198 diff --git a/providers/requesty/models/gpt-5@eu.toml b/providers/requesty/models/gpt-5@eu.toml index c03d73bc5..e694ec441 100644 --- a/providers/requesty/models/gpt-5@eu.toml +++ b/providers/requesty/models/gpt-5@eu.toml @@ -9,6 +9,6 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 1.375 -output = 11 -cache_read = 0.1375 +input = 1.2375 +output = 9.9 +cache_read = 0.12375 diff --git a/providers/requesty/models/grok-4.2-beta.toml b/providers/requesty/models/grok-4.2-beta.toml index 6577aa20d..bd3edb620 100644 --- a/providers/requesty/models/grok-4.2-beta.toml +++ b/providers/requesty/models/grok-4.2-beta.toml @@ -17,17 +17,17 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 2 -output = 6 -cache_read = 0.2 -cache_write = 2 +input = 1.8 +output = 5.4 +cache_read = 0.18 +cache_write = 1.8 [[cost.tiers]] tier = { type = "context", size = 200_000 } -input = 4 -output = 12 -cache_read = 0.4 -cache_write = 4 +input = 3.6 +output = 10.8 +cache_read = 0.36 +cache_write = 3.6 [limit] context = 2_000_000 diff --git a/providers/requesty/models/grok-4.3.toml b/providers/requesty/models/grok-4.3.toml index c9f02e4ee..19ecb03ea 100644 --- a/providers/requesty/models/grok-4.3.toml +++ b/providers/requesty/models/grok-4.3.toml @@ -8,17 +8,17 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 1.25 -output = 2.5 -cache_read = 0.2 -cache_write = 1.25 +input = 1.125 +output = 2.25 +cache_read = 0.18 +cache_write = 1.125 [[cost.tiers]] tier = { type = "context", size = 200_000 } -input = 2.5 -output = 5 -cache_read = 0.4 -cache_write = 2.5 +input = 2.25 +output = 4.5 +cache_read = 0.36 +cache_write = 2.25 [limit] output = 1_000_000 diff --git a/providers/requesty/models/grok-4.5.toml b/providers/requesty/models/grok-4.5.toml index 3d6bd0b85..4e20a50c6 100644 --- a/providers/requesty/models/grok-4.5.toml +++ b/providers/requesty/models/grok-4.5.toml @@ -8,14 +8,14 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 2 -output = 6 -cache_read = 0.5 -cache_write = 2 +input = 1.8 +output = 5.4 +cache_read = 0.45 +cache_write = 1.8 [[cost.tiers]] tier = { type = "context", size = 200_000 } -input = 4 -output = 12 -cache_read = 1 -cache_write = 4 +input = 3.6 +output = 10.8 +cache_read = 0.9 +cache_write = 3.6 diff --git a/providers/requesty/models/grok-4.6.toml b/providers/requesty/models/grok-4.6.toml index 9f48a48a7..3d9a628cd 100644 --- a/providers/requesty/models/grok-4.6.toml +++ b/providers/requesty/models/grok-4.6.toml @@ -8,14 +8,14 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 2 -output = 6 -cache_read = 0.5 -cache_write = 2 +input = 1.8 +output = 5.4 +cache_read = 0.45 +cache_write = 1.8 [[cost.tiers]] tier = { type = "context", size = 200_000 } -input = 4 -output = 12 -cache_read = 1 -cache_write = 4 +input = 3.6 +output = 10.8 +cache_read = 0.9 +cache_write = 3.6 diff --git a/providers/requesty/models/grok-build-0.1.toml b/providers/requesty/models/grok-build-0.1.toml index 1fbae2614..580edcd07 100644 --- a/providers/requesty/models/grok-build-0.1.toml +++ b/providers/requesty/models/grok-build-0.1.toml @@ -2,6 +2,6 @@ base_model = "xai/grok-build-0.1" reasoning = false [cost] -input = 1 -output = 2 -cache_read = 0.1 +input = 0.9 +output = 1.8 +cache_read = 0.09 diff --git a/providers/requesty/models/hy3.toml b/providers/requesty/models/hy3.toml index c6be2366f..d8e372d57 100644 --- a/providers/requesty/models/hy3.toml +++ b/providers/requesty/models/hy3.toml @@ -9,9 +9,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.14 -output = 0.58 -cache_read = 0.035 +input = 0.126 +output = 0.522 +cache_read = 0.0315 [limit] context = 262_144 diff --git a/providers/requesty/models/inkling-256k.toml b/providers/requesty/models/inkling-256k.toml index 45e77a32f..fd1df26c0 100644 --- a/providers/requesty/models/inkling-256k.toml +++ b/providers/requesty/models/inkling-256k.toml @@ -16,9 +16,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 1.87 -output = 4.68 -cache_read = 0.374 +input = 1.496 +output = 3.744 +cache_read = 0.2992 [limit] context = 262_144 diff --git a/providers/requesty/models/inkling.toml b/providers/requesty/models/inkling.toml index 65b2371a2..428a090ba 100644 --- a/providers/requesty/models/inkling.toml +++ b/providers/requesty/models/inkling.toml @@ -9,9 +9,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 1.87 -output = 4.68 -cache_read = 0.374 +input = 1.683 +output = 4.212 +cache_read = 0.3366 [limit] context = 65_536 diff --git a/providers/requesty/models/kat-coder-pro.toml b/providers/requesty/models/kat-coder-pro.toml index 3ec47a7db..c390576ce 100644 --- a/providers/requesty/models/kat-coder-pro.toml +++ b/providers/requesty/models/kat-coder-pro.toml @@ -10,8 +10,8 @@ structured_output = false open_weights = false [cost] -input = 0.3 -output = 1.2 +input = 0.27 +output = 1.08 [limit] context = 256_000 diff --git a/providers/requesty/models/kimi-k2.6.toml b/providers/requesty/models/kimi-k2.6.toml index e29bfdedc..279bf6221 100644 --- a/providers/requesty/models/kimi-k2.6.toml +++ b/providers/requesty/models/kimi-k2.6.toml @@ -8,6 +8,6 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.95 -output = 4 -cache_read = 0.16 +input = 0.855 +output = 3.6 +cache_read = 0.144 diff --git a/providers/requesty/models/kimi-k2.6@eu.toml b/providers/requesty/models/kimi-k2.6@eu.toml index 9770226aa..9ce827e89 100644 --- a/providers/requesty/models/kimi-k2.6@eu.toml +++ b/providers/requesty/models/kimi-k2.6@eu.toml @@ -9,9 +9,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.95 -output = 4 -cache_read = 0.95 +input = 0.855 +output = 3.6 +cache_read = 0.855 [limit] context = 256_000 diff --git a/providers/requesty/models/kimi-k2.7-code.toml b/providers/requesty/models/kimi-k2.7-code.toml index 7dae44e6f..cd6be544d 100644 --- a/providers/requesty/models/kimi-k2.7-code.toml +++ b/providers/requesty/models/kimi-k2.7-code.toml @@ -8,6 +8,6 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.95 -output = 4 -cache_read = 0.19 +input = 0.855 +output = 3.6 +cache_read = 0.171 diff --git a/providers/requesty/models/kimi-k2.7-code@eu.toml b/providers/requesty/models/kimi-k2.7-code@eu.toml index 411c07735..9037afe92 100644 --- a/providers/requesty/models/kimi-k2.7-code@eu.toml +++ b/providers/requesty/models/kimi-k2.7-code@eu.toml @@ -9,6 +9,6 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 1.25 -output = 4.5 -cache_read = 0.31 +input = 1.125 +output = 4.05 +cache_read = 0.279 diff --git a/providers/requesty/models/kimi-k3.toml b/providers/requesty/models/kimi-k3.toml index b1999cda9..3bb366be1 100644 --- a/providers/requesty/models/kimi-k3.toml +++ b/providers/requesty/models/kimi-k3.toml @@ -8,9 +8,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 2.25 -output = 11.25 -cache_read = 0.225 +input = 2.025 +output = 10.125 +cache_read = 0.2025 [limit] output = 262_144 diff --git a/providers/requesty/models/kimi-k3@eu.toml b/providers/requesty/models/kimi-k3@eu.toml index bb3b72388..92428865b 100644 --- a/providers/requesty/models/kimi-k3@eu.toml +++ b/providers/requesty/models/kimi-k3@eu.toml @@ -9,9 +9,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 2.25 -output = 11.25 -cache_read = 0.225 +input = 2.025 +output = 10.125 +cache_read = 0.2025 [limit] output = 262_144 diff --git a/providers/requesty/models/ling-2.6-1t.toml b/providers/requesty/models/ling-2.6-1t.toml index c85bef2c3..6d03156b1 100644 --- a/providers/requesty/models/ling-2.6-1t.toml +++ b/providers/requesty/models/ling-2.6-1t.toml @@ -10,8 +10,8 @@ structured_output = false open_weights = false [cost] -input = 0.3 -output = 2.5 +input = 0.27 +output = 2.25 [limit] context = 262_144 diff --git a/providers/requesty/models/ling-2.6-flash.toml b/providers/requesty/models/ling-2.6-flash.toml index 87bbeddcb..fbcfbe27c 100644 --- a/providers/requesty/models/ling-2.6-flash.toml +++ b/providers/requesty/models/ling-2.6-flash.toml @@ -10,8 +10,8 @@ structured_output = false open_weights = false [cost] -input = 0.1 -output = 0.3 +input = 0.09 +output = 0.27 [limit] context = 262_144 diff --git a/providers/requesty/models/mimo-v2.5-pro.toml b/providers/requesty/models/mimo-v2.5-pro.toml index 96a7a3599..808477589 100644 --- a/providers/requesty/models/mimo-v2.5-pro.toml +++ b/providers/requesty/models/mimo-v2.5-pro.toml @@ -3,6 +3,6 @@ reasoning = false structured_output = false [cost] -input = 0.435 -output = 0.87 -cache_read = 0.0036 +input = 0.3915 +output = 0.783 +cache_read = 0.00324 diff --git a/providers/requesty/models/mimo-v2.5.toml b/providers/requesty/models/mimo-v2.5.toml index 4ba7b3143..7c4ac60ea 100644 --- a/providers/requesty/models/mimo-v2.5.toml +++ b/providers/requesty/models/mimo-v2.5.toml @@ -3,6 +3,6 @@ reasoning = false structured_output = false [cost] -input = 0.14 -output = 0.28 -cache_read = 0.0028 +input = 0.126 +output = 0.252 +cache_read = 0.00252 diff --git a/providers/requesty/models/minimax-m2.7-highspeed.toml b/providers/requesty/models/minimax-m2.7-highspeed.toml index d13335dcd..505b7a466 100644 --- a/providers/requesty/models/minimax-m2.7-highspeed.toml +++ b/providers/requesty/models/minimax-m2.7-highspeed.toml @@ -9,10 +9,10 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.6 -output = 2.4 -cache_read = 0.06 -cache_write = 1.2 +input = 0.54 +output = 2.16 +cache_read = 0.054 +cache_write = 1.08 [limit] context = 200_000 diff --git a/providers/requesty/models/minimax-m2.7.toml b/providers/requesty/models/minimax-m2.7.toml index 2245aa853..b650b63f6 100644 --- a/providers/requesty/models/minimax-m2.7.toml +++ b/providers/requesty/models/minimax-m2.7.toml @@ -9,10 +9,10 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.3 -output = 1.2 -cache_read = 0.06 -cache_write = 1.2 +input = 0.27 +output = 1.08 +cache_read = 0.054 +cache_write = 1.08 [limit] context = 200_000 diff --git a/providers/requesty/models/minimax-m3.toml b/providers/requesty/models/minimax-m3.toml index 137e587dc..3c8106a29 100644 --- a/providers/requesty/models/minimax-m3.toml +++ b/providers/requesty/models/minimax-m3.toml @@ -9,9 +9,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.3 -output = 1.2 -cache_read = 0.06 +input = 0.24 +output = 0.96 +cache_read = 0.048 [limit] context = 1_000_000 diff --git a/providers/requesty/models/minimax-m3@eu.toml b/providers/requesty/models/minimax-m3@eu.toml index 7a239b4b0..738401ce5 100644 --- a/providers/requesty/models/minimax-m3@eu.toml +++ b/providers/requesty/models/minimax-m3@eu.toml @@ -10,9 +10,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.4 -output = 2 -cache_read = 0.1 +input = 0.36 +output = 1.8 +cache_read = 0.09 [limit] context = 1_048_576 diff --git a/providers/requesty/models/mistral-medium-3-5.toml b/providers/requesty/models/mistral-medium-3-5.toml index 846955e7d..cd3cc407a 100644 --- a/providers/requesty/models/mistral-medium-3-5.toml +++ b/providers/requesty/models/mistral-medium-3-5.toml @@ -17,9 +17,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 1.65 -output = 8.25 -cache_read = 1.65 +input = 1.485 +output = 7.425 +cache_read = 1.485 [limit] context = 262_144 diff --git a/providers/requesty/models/mistral-medium-3-5@eu.toml b/providers/requesty/models/mistral-medium-3-5@eu.toml index 41dfecc58..ad3d129f3 100644 --- a/providers/requesty/models/mistral-medium-3-5@eu.toml +++ b/providers/requesty/models/mistral-medium-3-5@eu.toml @@ -17,9 +17,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 1.65 -output = 8.25 -cache_read = 1.65 +input = 1.485 +output = 7.425 +cache_read = 1.485 [limit] context = 262_144 diff --git a/providers/requesty/models/mistral-medium-latest.toml b/providers/requesty/models/mistral-medium-latest.toml index e841391c8..1cc3aa691 100644 --- a/providers/requesty/models/mistral-medium-latest.toml +++ b/providers/requesty/models/mistral-medium-latest.toml @@ -2,9 +2,9 @@ base_model = "mistral/mistral-medium-latest" reasoning = false [cost] -input = 0.44 -output = 2.2 -cache_read = 0.44 +input = 0.396 +output = 1.98 +cache_read = 0.396 [limit] context = 131_072 diff --git a/providers/requesty/models/mistral-medium-latest@eu.toml b/providers/requesty/models/mistral-medium-latest@eu.toml index 406cd9716..5ca123b94 100644 --- a/providers/requesty/models/mistral-medium-latest@eu.toml +++ b/providers/requesty/models/mistral-medium-latest@eu.toml @@ -3,9 +3,9 @@ name = "Mistral Medium (latest) (EU)" reasoning = false [cost] -input = 0.44 -output = 2.2 -cache_read = 0.44 +input = 0.396 +output = 1.98 +cache_read = 0.396 [limit] context = 131_072 diff --git a/providers/requesty/models/mistral-small-2603.toml b/providers/requesty/models/mistral-small-2603.toml index 7a4b26451..cae2472d8 100644 --- a/providers/requesty/models/mistral-small-2603.toml +++ b/providers/requesty/models/mistral-small-2603.toml @@ -9,6 +9,6 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.165 -output = 0.66 -cache_read = 0.165 +input = 0.1485 +output = 0.594 +cache_read = 0.1485 diff --git a/providers/requesty/models/mistral-small-2603@eu.toml b/providers/requesty/models/mistral-small-2603@eu.toml index 66339a037..345822d0a 100644 --- a/providers/requesty/models/mistral-small-2603@eu.toml +++ b/providers/requesty/models/mistral-small-2603@eu.toml @@ -10,6 +10,6 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.165 -output = 0.66 -cache_read = 0.165 +input = 0.1485 +output = 0.594 +cache_read = 0.1485 diff --git a/providers/requesty/models/nemotron-3-nano-omni.toml b/providers/requesty/models/nemotron-3-nano-omni.toml index f8ca025e6..575ee74c9 100644 --- a/providers/requesty/models/nemotron-3-nano-omni.toml +++ b/providers/requesty/models/nemotron-3-nano-omni.toml @@ -17,9 +17,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.06 -output = 0.24 -cache_read = 0.06 +input = 0.054 +output = 0.216 +cache_read = 0.054 [limit] context = 300_000 diff --git a/providers/requesty/models/nemotron-3-nano-omni@eu.toml b/providers/requesty/models/nemotron-3-nano-omni@eu.toml index 1422a67a6..68fc6a8b2 100644 --- a/providers/requesty/models/nemotron-3-nano-omni@eu.toml +++ b/providers/requesty/models/nemotron-3-nano-omni@eu.toml @@ -17,9 +17,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.06 -output = 0.24 -cache_read = 0.06 +input = 0.054 +output = 0.216 +cache_read = 0.054 [limit] context = 300_000 diff --git a/providers/requesty/models/nemotron-3-ultra-nvfp4.toml b/providers/requesty/models/nemotron-3-ultra-nvfp4.toml index 3fc92c2cc..b0cbe8dfa 100644 --- a/providers/requesty/models/nemotron-3-ultra-nvfp4.toml +++ b/providers/requesty/models/nemotron-3-ultra-nvfp4.toml @@ -17,9 +17,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.6 -output = 2.4 -cache_read = 0.12 +input = 0.54 +output = 2.16 +cache_read = 0.108 [limit] context = 262_144 diff --git a/providers/requesty/models/nemotron-lightning-3.5-30b-a3b.toml b/providers/requesty/models/nemotron-lightning-3.5-30b-a3b.toml index d55a5302b..34588b5cc 100644 --- a/providers/requesty/models/nemotron-lightning-3.5-30b-a3b.toml +++ b/providers/requesty/models/nemotron-lightning-3.5-30b-a3b.toml @@ -17,9 +17,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.05 -output = 0.2 -cache_read = 0.01 +input = 0.045 +output = 0.18 +cache_read = 0.009 [limit] context = 262_144 diff --git a/providers/requesty/models/nvidia-nemotron-3-super-120b-a12b.toml b/providers/requesty/models/nvidia-nemotron-3-super-120b-a12b.toml index d7fbf31d0..6a0e782c9 100644 --- a/providers/requesty/models/nvidia-nemotron-3-super-120b-a12b.toml +++ b/providers/requesty/models/nvidia-nemotron-3-super-120b-a12b.toml @@ -17,8 +17,8 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.1 -output = 0.5 +input = 0.09 +output = 0.45 [limit] context = 262_144 diff --git a/providers/requesty/models/nvidia-nemotron-3-ultra.toml b/providers/requesty/models/nvidia-nemotron-3-ultra.toml index 92717df9c..844902a86 100644 --- a/providers/requesty/models/nvidia-nemotron-3-ultra.toml +++ b/providers/requesty/models/nvidia-nemotron-3-ultra.toml @@ -17,8 +17,8 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.5 -output = 2.5 +input = 0.45 +output = 2.25 [limit] context = 262_144 diff --git a/providers/requesty/models/o4-mini@eu.toml b/providers/requesty/models/o4-mini@eu.toml index 7e8324087..39db9fef8 100644 --- a/providers/requesty/models/o4-mini@eu.toml +++ b/providers/requesty/models/o4-mini@eu.toml @@ -9,6 +9,6 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 1.21 -output = 4.84 -cache_read = 0.3025 +input = 1.089 +output = 4.356 +cache_read = 0.27225 diff --git a/providers/requesty/models/qwen3.5-27b.toml b/providers/requesty/models/qwen3.5-27b.toml index e5366eb2b..bb7844b8e 100644 --- a/providers/requesty/models/qwen3.5-27b.toml +++ b/providers/requesty/models/qwen3.5-27b.toml @@ -8,8 +8,8 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.26 -output = 2.6 +input = 0.234 +output = 2.34 [limit] output = 262_144 diff --git a/providers/requesty/models/qwen3.5-2b.toml b/providers/requesty/models/qwen3.5-2b.toml index 781016ffc..dcb8bf202 100644 --- a/providers/requesty/models/qwen3.5-2b.toml +++ b/providers/requesty/models/qwen3.5-2b.toml @@ -17,8 +17,8 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.02 -output = 0.1 +input = 0.018 +output = 0.09 [limit] context = 262_144 diff --git a/providers/requesty/models/qwen3.5-35b-a3b.toml b/providers/requesty/models/qwen3.5-35b-a3b.toml index ca01a2e54..568c5343e 100644 --- a/providers/requesty/models/qwen3.5-35b-a3b.toml +++ b/providers/requesty/models/qwen3.5-35b-a3b.toml @@ -8,9 +8,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.14 -output = 1 -cache_read = 0.05 +input = 0.126 +output = 0.9 +cache_read = 0.045 [limit] output = 262_144 diff --git a/providers/requesty/models/qwen3.6-plus.toml b/providers/requesty/models/qwen3.6-plus.toml index c9b20433c..fac83531f 100644 --- a/providers/requesty/models/qwen3.6-plus.toml +++ b/providers/requesty/models/qwen3.6-plus.toml @@ -9,7 +9,7 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.5 -output = 3 -cache_read = 0.05 -cache_write = 0.625 +input = 0.45 +output = 2.7 +cache_read = 0.045 +cache_write = 0.5625 diff --git a/providers/requesty/models/qwen3.7-max.toml b/providers/requesty/models/qwen3.7-max.toml index b0d779243..b6205364f 100644 --- a/providers/requesty/models/qwen3.7-max.toml +++ b/providers/requesty/models/qwen3.7-max.toml @@ -9,10 +9,10 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 2.5 -output = 7.5 -cache_read = 0.25 -cache_write = 3.125 +input = 2.25 +output = 6.75 +cache_read = 0.225 +cache_write = 2.8125 [limit] context = 1_048_576 diff --git a/providers/requesty/models/qwen3.7-plus.toml b/providers/requesty/models/qwen3.7-plus.toml index 009846440..7e53c0a59 100644 --- a/providers/requesty/models/qwen3.7-plus.toml +++ b/providers/requesty/models/qwen3.7-plus.toml @@ -9,10 +9,10 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.32 -output = 1.28 -cache_read = 0.032 -cache_write = 0.4 +input = 0.28 +output = 1.12 +cache_read = 0.028 +cache_write = 0.35 [limit] context = 1_048_576 diff --git a/providers/requesty/models/qwen3.8-2.4T-A95B.toml b/providers/requesty/models/qwen3.8-2.4T-A95B.toml index a28dc96e2..02cdb3ba6 100644 --- a/providers/requesty/models/qwen3.8-2.4T-A95B.toml +++ b/providers/requesty/models/qwen3.8-2.4T-A95B.toml @@ -8,9 +8,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 2 -output = 6 -cache_read = 0.2 +input = 1.8 +output = 5.4 +cache_read = 0.18 [limit] output = 262_144 diff --git a/providers/requesty/models/qwen3.8-max.toml b/providers/requesty/models/qwen3.8-max.toml index c9f9d76a6..bfc96dcb1 100644 --- a/providers/requesty/models/qwen3.8-max.toml +++ b/providers/requesty/models/qwen3.8-max.toml @@ -9,10 +9,10 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 2 -output = 6 -cache_read = 0.25 -cache_write = 2.5 +input = 1.8 +output = 5.4 +cache_read = 0.225 +cache_write = 2.25 [limit] context = 1_048_576 diff --git a/providers/requesty/models/ring-2.6-1t.toml b/providers/requesty/models/ring-2.6-1t.toml index 8f33bc846..fed1a0ad2 100644 --- a/providers/requesty/models/ring-2.6-1t.toml +++ b/providers/requesty/models/ring-2.6-1t.toml @@ -17,8 +17,8 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.3 -output = 2.5 +input = 0.27 +output = 2.25 [limit] context = 262_144 diff --git a/providers/requesty/models/seed-1.8.toml b/providers/requesty/models/seed-1.8.toml index 2472c31bb..4b8470af3 100644 --- a/providers/requesty/models/seed-1.8.toml +++ b/providers/requesty/models/seed-1.8.toml @@ -17,9 +17,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.25 -output = 2 -cache_read = 0.05 +input = 0.225 +output = 1.8 +cache_read = 0.045 [limit] context = 256_000 diff --git a/providers/requesty/models/seed-2.0-code.toml b/providers/requesty/models/seed-2.0-code.toml index c64d1a091..252f4fa5c 100644 --- a/providers/requesty/models/seed-2.0-code.toml +++ b/providers/requesty/models/seed-2.0-code.toml @@ -9,9 +9,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.5 -output = 3 -cache_read = 0.1 +input = 0.45 +output = 2.7 +cache_read = 0.09 [limit] context = 256_000 diff --git a/providers/requesty/models/seed-2.0-mini.toml b/providers/requesty/models/seed-2.0-mini.toml index 4e3dfb0ea..86f36d0d3 100644 --- a/providers/requesty/models/seed-2.0-mini.toml +++ b/providers/requesty/models/seed-2.0-mini.toml @@ -9,9 +9,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.1 -output = 0.4 -cache_read = 0.02 +input = 0.09 +output = 0.36 +cache_read = 0.018 [limit] output = 256_000 diff --git a/providers/requesty/models/seed-2.0-pro.toml b/providers/requesty/models/seed-2.0-pro.toml index b7091c5fb..f4d76fe61 100644 --- a/providers/requesty/models/seed-2.0-pro.toml +++ b/providers/requesty/models/seed-2.0-pro.toml @@ -9,9 +9,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.5 -output = 3 -cache_read = 0.1 +input = 0.45 +output = 2.7 +cache_read = 0.09 [limit] output = 256_000 diff --git a/providers/requesty/models/step-3.7-flash.toml b/providers/requesty/models/step-3.7-flash.toml index 10e1b1afb..cd2b74f8b 100644 --- a/providers/requesty/models/step-3.7-flash.toml +++ b/providers/requesty/models/step-3.7-flash.toml @@ -10,9 +10,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.2 -output = 1.15 -cache_read = 0.04 +input = 0.18 +output = 1.035 +cache_read = 0.036 [limit] context = 262_144 diff --git a/providers/requesty/models/thinkingcap-qwen3.6-27b.toml b/providers/requesty/models/thinkingcap-qwen3.6-27b.toml index b34410d39..9810394d7 100644 --- a/providers/requesty/models/thinkingcap-qwen3.6-27b.toml +++ b/providers/requesty/models/thinkingcap-qwen3.6-27b.toml @@ -17,9 +17,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.4 -output = 3 -cache_read = 0.26 +input = 0.36 +output = 2.7 +cache_read = 0.234 [limit] context = 262_144 diff --git a/providers/requesty/models/thinkingcap-qwen3.6-27b@eu.toml b/providers/requesty/models/thinkingcap-qwen3.6-27b@eu.toml index ba21875fd..0f5cc42ea 100644 --- a/providers/requesty/models/thinkingcap-qwen3.6-27b@eu.toml +++ b/providers/requesty/models/thinkingcap-qwen3.6-27b@eu.toml @@ -17,9 +17,9 @@ values = ["none", "low", "medium", "high", "max"] type = "budget_tokens" [cost] -input = 0.4 -output = 3 -cache_read = 0.26 +input = 0.36 +output = 2.7 +cache_read = 0.234 [limit] context = 262_144